Toward a language modeling approach for consumer review spam detection

C. L. Lai; K. Q. Xu; Raymond Y.K. Lau; Y. Li; L. Jing

doi:10.1109/ICEBE.2010.47

Toward a language modeling approach for consumer review spam detection

C. L. Lai, K. Q. Xu, Raymond Y.K. Lau, Y. Li, L. Jing

Department of Information Systems

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

55 Citations (Scopus)

Abstract

Numerous reports have indicated the severity of fake reviews (i.e., spam) posted to various e-Commerce or opinion sharing Web sites. Nevertheless, very few studies have been conducted to examine the trustworthiness of online consumer reviews because of the lack of an effective computational methodology. Unlike other kinds of Web spam, untruthful reviews could just look like other legitimate reviews (i.e., ham), and so it is difficult to apply any features to distinguish the two classes. One main contribution of our research work is the development of a novel computational methodology to combat online review spam. Our experimental results confirm that the KL divergence and the probabilistic language modeling based computational model is effective for the detection of untruthful reviews. Empowered by the proposed computational methods, our empirical study found that around 2% of the consumer reviews posted to a large e-Commerce site is spam. © 2010 IEEE.

Original language	English
Title of host publication	Proceedings - IEEE International Conference on E-Business Engineering, ICEBE 2010
Pages	1-8
DOIs	https://doi.org/10.1109/ICEBE.2010.47
Publication status	Published - 2010
Event	IEEE International Conference on E-Business Engineering, ICEBE 2010 - Shanghai, China Duration: 10 Nov 2010 → 12 Nov 2010

Conference

Conference	IEEE International Conference on E-Business Engineering, ICEBE 2010
Place	China
City	Shanghai
Period	10/11/10 → 12/11/10

Research Keywords

Electronic commerce
Kullback-Leibler divergence
Language models
Review spam
Spam detection

Access Output

10.1109/ICEBE.2010.47

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{93c248eec8a84f03849b208516afeee5,

title = "Toward a language modeling approach for consumer review spam detection",

abstract = "Numerous reports have indicated the severity of fake reviews (i.e., spam) posted to various e-Commerce or opinion sharing Web sites. Nevertheless, very few studies have been conducted to examine the trustworthiness of online consumer reviews because of the lack of an effective computational methodology. Unlike other kinds of Web spam, untruthful reviews could just look like other legitimate reviews (i.e., ham), and so it is difficult to apply any features to distinguish the two classes. One main contribution of our research work is the development of a novel computational methodology to combat online review spam. Our experimental results confirm that the KL divergence and the probabilistic language modeling based computational model is effective for the detection of untruthful reviews. Empowered by the proposed computational methods, our empirical study found that around 2% of the consumer reviews posted to a large e-Commerce site is spam. {\textcopyright} 2010 IEEE.",

keywords = "Electronic commerce, Kullback-Leibler divergence, Language models, Review spam, Spam detection",

author = "Lai, {C. L.} and Xu, {K. Q.} and Lau, {Raymond Y.K.} and Y. Li and L. Jing",

year = "2010",

doi = "10.1109/ICEBE.2010.47",

language = "English",

isbn = "9780769542270",

pages = "1--8",

booktitle = "Proceedings - IEEE International Conference on E-Business Engineering, ICEBE 2010",

note = "IEEE International Conference on E-Business Engineering, ICEBE 2010 ; Conference date: 10-11-2010 Through 12-11-2010",

}

Toward a language modeling approach for consumer review spam detection. / Lai, C. L.; Xu, K. Q.; Lau, Raymond Y.K. et al.
Proceedings - IEEE International Conference on E-Business Engineering, ICEBE 2010. 2010. p. 1-8 5704291.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Toward a language modeling approach for consumer review spam detection

AU - Lai, C. L.

AU - Xu, K. Q.

AU - Lau, Raymond Y.K.

AU - Li, Y.

AU - Jing, L.

PY - 2010

Y1 - 2010

N2 - Numerous reports have indicated the severity of fake reviews (i.e., spam) posted to various e-Commerce or opinion sharing Web sites. Nevertheless, very few studies have been conducted to examine the trustworthiness of online consumer reviews because of the lack of an effective computational methodology. Unlike other kinds of Web spam, untruthful reviews could just look like other legitimate reviews (i.e., ham), and so it is difficult to apply any features to distinguish the two classes. One main contribution of our research work is the development of a novel computational methodology to combat online review spam. Our experimental results confirm that the KL divergence and the probabilistic language modeling based computational model is effective for the detection of untruthful reviews. Empowered by the proposed computational methods, our empirical study found that around 2% of the consumer reviews posted to a large e-Commerce site is spam. © 2010 IEEE.

AB - Numerous reports have indicated the severity of fake reviews (i.e., spam) posted to various e-Commerce or opinion sharing Web sites. Nevertheless, very few studies have been conducted to examine the trustworthiness of online consumer reviews because of the lack of an effective computational methodology. Unlike other kinds of Web spam, untruthful reviews could just look like other legitimate reviews (i.e., ham), and so it is difficult to apply any features to distinguish the two classes. One main contribution of our research work is the development of a novel computational methodology to combat online review spam. Our experimental results confirm that the KL divergence and the probabilistic language modeling based computational model is effective for the detection of untruthful reviews. Empowered by the proposed computational methods, our empirical study found that around 2% of the consumer reviews posted to a large e-Commerce site is spam. © 2010 IEEE.

KW - Electronic commerce

KW - Kullback-Leibler divergence

KW - Language models

KW - Review spam

KW - Spam detection

UR - http://www.scopus.com/inward/record.url?scp=79951782094&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-79951782094&origin=recordpage

U2 - 10.1109/ICEBE.2010.47

DO - 10.1109/ICEBE.2010.47

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9780769542270

SP - 1

EP - 8

BT - Proceedings - IEEE International Conference on E-Business Engineering, ICEBE 2010

T2 - IEEE International Conference on E-Business Engineering, ICEBE 2010

Y2 - 10 November 2010 through 12 November 2010

ER -

Toward a language modeling approach for consumer review spam detection

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this